index.js

var underscore = require('underscore');
var replay = async function (batchSize, index) {
  var minibatch = [];

  if (index === subzeroIndex) { 
    minibatch = underscore.sample(subzeroMemory, batchSize);
  } else {
    minibatch = underscore.sample(kanoMemory, batchSize);
  }

  for (var i = 0; i < minibatch.length; i++) {

    // deconstructs secuence
    var { state, action, reward, nextState, done } = minibatch[i];

    // predicts action
    var tensorState = stateToTensor(state, index);
    target = model.predict(tensorState);

    if (done) {
      target.dataSync()[action] = reward;
    } else {
      var tensorNextState = stateToTensor(nextState, index);
      t = targetModel.predict(tensorNextState).dataSync();
      target.dataSync()[action] = reward + gamma * Math.max(...t);
    }
    await model.fit(tensorState, target);
  }

  if (epsilon > epsilonMin) { 
    epsilon *= epsilonDecay;
  }
}